| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.042105263157894736, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004678362573099415, | |
| "grad_norm": 1.7253204584121704, | |
| "learning_rate": 2e-05, | |
| "loss": 3.0201, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004678362573099415, | |
| "eval_loss": 0.8125972151756287, | |
| "eval_runtime": 3.9867, | |
| "eval_samples_per_second": 22.575, | |
| "eval_steps_per_second": 11.287, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00935672514619883, | |
| "grad_norm": 1.611464500427246, | |
| "learning_rate": 4e-05, | |
| "loss": 3.3405, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 1.4793864488601685, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4403, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "eval_loss": 0.8083972334861755, | |
| "eval_runtime": 3.9773, | |
| "eval_samples_per_second": 22.628, | |
| "eval_steps_per_second": 11.314, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01871345029239766, | |
| "grad_norm": 1.2403775453567505, | |
| "learning_rate": 8e-05, | |
| "loss": 3.0677, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 1.1208009719848633, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9597, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "grad_norm": 1.4384738206863403, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9013, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "eval_loss": 0.7677449584007263, | |
| "eval_runtime": 4.0343, | |
| "eval_samples_per_second": 22.309, | |
| "eval_steps_per_second": 11.154, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03274853801169591, | |
| "grad_norm": 1.2731095552444458, | |
| "learning_rate": 0.00014, | |
| "loss": 3.1716, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03742690058479532, | |
| "grad_norm": 1.1444038152694702, | |
| "learning_rate": 0.00016, | |
| "loss": 3.219, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 0.9928809404373169, | |
| "learning_rate": 0.00018, | |
| "loss": 2.4574, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "eval_loss": 0.6846689581871033, | |
| "eval_runtime": 4.0345, | |
| "eval_samples_per_second": 22.308, | |
| "eval_steps_per_second": 11.154, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1285134728822784.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |